© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 79480
    Prev
    Next
    INDEX
    Explanations

    code and programming

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    理论
    -0.08
     effortless
    -0.08
     consentimiento
    -0.08
    _Params
    -0.08
     zapos
    -0.08
     stools
    -0.08
     Consent
    -0.08
    .Does
    -0.08
     discap
    -0.08
     atrop
    -0.08
    POSITIVE LOGITS
     thermometer
    0.09
    	system
    0.07
     système
    0.07
     Screenshot
    0.07
    	false
    0.07
    	location
    0.07
     screenshot
    0.07
     hatred
    0.07
     hostility
    0.07
     عنوان
    0.07
    Activations Density 0.003%

    No Known Activations